To address issues such as loss of detailed information, blurred target boundaries, and unclear structural hierarchy in medical image fusion, this paper proposes an adaptive feature medical image fusion network based on a full-scale diffusion model. First, a region-level feature map is generated using a kernel-based saliency map to enhance local features and boundary details. Then, a full-scale diffusion feature extraction network is employed for global feature extraction, alongside a multi-scale denoising U-shaped network designed to fully capture cross-layer information. A multi-scale feature integration module is introduced to reinforce texture details and structural information extracted by the encoder. Finally, an adaptive fusion scheme is applied to progressively fuse region-level features, global features, and source images layer by layer, enhancing the preservation of detail information. To validate the effectiveness of the proposed method, this paper validates the proposed model on the publicly available Harvard dataset and an abdominal dataset. By comparing with nine other representative image fusion methods, the proposed approach achieved improvements across seven evaluation metrics. The results demonstrate that the proposed method effectively extracts both global and local features of medical images, enhances texture details and target boundary clarity, and generates fusion image with high contrast and rich information, providing more reliable support for subsequent clinical diagnosis.
Humans ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Neural Networks, Computer ; Diagnostic Imaging/methods* ; Image Interpretation, Computer-Assisted/methods*

Objective To analyze the changes of coagulation indexes in patients of non-valvular atrial fibrillation with different ABO blood types before and after treatment with the new oral anticoag-ulant dabigatran etexilate.Methods A total of 100 patients with non-valvular atrial fibrillation were selected as research subjects,and they were divided into type O group(n=50)and non-type 0 group(n=50)according to blood types,and dabigatran etexilate capsules were given to both groups.The coagulation function indexes of the two groups after 3 months were compared.Results Before treatment,there were significant differences in Von Willebrand factor(vWF)and protein C activities between two groups(P＜0.05).After treatment,the activities of vWF and protein C showed signifi-cant differences between two groups(P＜0.05).Before treatment,there was no significant differ-ence in activated partial thromboplastin time(APTT)between the two groups(P＞0.05),but there was a significant difference in APTT between the two groups after treatment(P＜0.05).There were no significant between-group differences in plasma prothrombin time(PT),thrombin time(TT),in-ternational normalized ratio(INR)and coagulation factor Ⅷ before and after treatment(P＞0.05).There were significant differences in all coagulation related indexes between the two groups after treat-ment compared with treatment before(P＜0.05).Conclusion Patients with type O blood are more likely to alert to occurrence of bleeding events when treated with dabigatran etexilate,and can be pre-dicted by APTT and protein C activity to some extent.

Objective To analyze the changes of coagulation indexes in patients of non-valvular atrial fibrillation with different ABO blood types before and after treatment with the new oral anticoag-ulant dabigatran etexilate.Methods A total of 100 patients with non-valvular atrial fibrillation were selected as research subjects,and they were divided into type O group(n=50)and non-type 0 group(n=50)according to blood types,and dabigatran etexilate capsules were given to both groups.The coagulation function indexes of the two groups after 3 months were compared.Results Before treatment,there were significant differences in Von Willebrand factor(vWF)and protein C activities between two groups(P＜0.05).After treatment,the activities of vWF and protein C showed signifi-cant differences between two groups(P＜0.05).Before treatment,there was no significant differ-ence in activated partial thromboplastin time(APTT)between the two groups(P＞0.05),but there was a significant difference in APTT between the two groups after treatment(P＜0.05).There were no significant between-group differences in plasma prothrombin time(PT),thrombin time(TT),in-ternational normalized ratio(INR)and coagulation factor Ⅷ before and after treatment(P＞0.05).There were significant differences in all coagulation related indexes between the two groups after treat-ment compared with treatment before(P＜0.05).Conclusion Patients with type O blood are more likely to alert to occurrence of bleeding events when treated with dabigatran etexilate,and can be pre-dicted by APTT and protein C activity to some extent.

Objective:To evaluate the technical approach and application value of DynaCT biliary reconstruction with CT images fusion (DynaCT-CT fusion) for the treatment of complex hepatolithiasis.Methods:The data of 18 patients with complex hepatolithiasis admitted to the First Affiliated Hospital of Guangzhou Medical University from May 2022 to October 2022 were retrospectively analyzed, including 7 males and 11 females, aged (50.6±15.0) years. Preoperative DynaCT biliary reconstruction with CT images fusion was performed to guide the percutaneous transhepatic one-step biliary fistulation (PTOBF). The technical data, including the bile duct with stones identified by preoperative imaging, the actual bile duct with stones confirmed intraoperatively, the satisfied stone removal time for each targeted bile duct, the actual stone removal time for each targeted bile duct, the intraoperative identification of CT-negative stones, the postoperative complications and reoperation were analyzed.Results:In 18 patients, a total of 95 target bile ducts with stones were identified by preoperative DynaCT-CT fusion technology, involving the first, secondary and tertiary bile ducts. Preoperative CT identified 29 lesions of stones involving the first and secondary bile ducts. CT negative stones were confirmed in 5 patients by DynaCT-CT fusion. Bile duct stricture occurred in 12 patients. All procedures were completed without postoperative bile leakage or hemorrhage. A total of 82 lesions of stones were successfully removed with a removal time of (25.9±12.8) min. The satisfied stone removal time for each targeted bile duct was (10.1±7.6) min, and the actual stone removal time was (10.5±7.4) min. Immediate stone clearance was achieved in 13 patients. Biliary tract infection occurred in 2 patients, and 5 patients underwent reoperation for residual or recurrent stones.Conclusion:The DynaCT-CT fusion technology guided PTOBF is feasible and safe in patients with complex hepatolithiasis. It could effectively detect more stones, shorten the stone clearance time. DynaCT-CT fusion technology provides a new strategy for the treatment of hepatolithiasis.

Objective:To explore the clinical characteristics and predictors of severe acute pancreatitis complicated with acute respiratory distress syndrome (SAP-ARDS).Methods:Clinical data of consecutive 313 SAP patients hospitalized from January 2000 to January 2020 in Peking Union Medical College Hospital, were retrospectively analyzed, including 258 cases with ARDS (ARDS group) and 55 cases without ARDS (non-ARDS group). According to the severity of ARDS, ARDS group were further divided into mild ARDS group (165 cases) and moderate to severe ARDS group (93 cases). Clinical symptoms, laboratory examination and imaging results, ICU admission time and clinical outcome, as well as the local and systemic complications, acute physiology and chronic health evaluation (APACHEⅡ) within 24 h after admission, bedside index for severity in acute pancreatitis (BISAP), CT severity index (CTSI), sequential organ failure assessment (SOFA) and quick sequenctial organ failure assessment(qSOFA) score were recorded. Univariate and multivariate logistic regression were performed to analyze independent risk factors of SAP complicated with moderate to severe ARDS. Receiver operating characteristics curves (ROC) was drawn to calculate area under the ROC curve (area under curve, AUC) and evaluate the performance of WBC and hsCRP in predicting SAP complicated with moderate to severe ARDS, and assess the performance of APACHEⅡ, BISAP, CTSI, SOFA and qSOFA scores in predicting SAP-ARDS endotracheal intubation.Results:The ICU length of stay and mortality rate of SAP-ARDS patients were significantly higher than those without ARDS [(8.3±11.6 day vs 5.7±7.7 day, 12.4% vs 3.6%, all P value <0.05)]. Univariate analysis showed that elevated WBC ( OR 4.52, 95% CI 1.64-12.4) and hsCRP ( OR 3.69, 95% CI 1.29-10.48) on admission were independent risk factors for moderate to severe ARDS with SAP. The AUC of WBC and hsCRP for predicting SAP with moderate to severe ARDS at admission were 0.651(95% CI 0.532-0.770) and 0.615 (95% CI 0.500-0.730), respectively. The predicted cut-off values (Cut-off values) were 17.5×10 9/L and 159 mg/L, respectively, and the sensitivity was 53.1% and 78.1%, the specificity was 78.1% and 48.4% respectively. The area under the ROC curve for APACHEⅡ, BISAP, CTSI, SOFA, and qSOFA score 24 h after admission in the early prediction of endotracheal intubation were 0.739 (95% CI 0.626-0.840), 0.705 (95% CI 0.602-0.809), 0.753 (95% CI 0.650-0.849 ), 0.737 (95% CI 0.615-0.836) and 0.663 (95% CI 0.570-0.794), and the optimum Cut-off values were 14 points, 3 points, 5 points, 7 points, 2 points, and the sensitivity and specificity for these predictors were 58.8% and 81.4%, 79.4% and 60.0%, 73.5% and 67.1%, 38.2% and 98.6%, 45.5% and 83.3%, respectively. Conclusions::Elevated blood WBC and hsCRP on admission were independent risk factors for moderate to severe ARDS in SAP. APACHEⅡ≥14, BISAP≥3, CTSI≥5, SOFA≥7, or qSOFA≥2 within the 24 h admission indictaed that the risk of SAP patients to receive endotracheal intubation was high.

Objective:To analyze the clinical-pathological data of patients with locally advanced rectal cancer who underwent modified total neoadjuvant therapy (TNT), and to evaluate the safety and efficacy of radical surgery after modified total neoadjuvant therapy.Methods:The clinical-pathological data of 30 locally advanced rectal cancer patients who underwent modified TNT (mTNT) followed by radical resection were retrospectively analyzed. The surgical procedure, postoperative complications, tumor regression grade, tumor downstaging and prognosis were analyzed.Results:The 30 patients included 24 males and 6 females with a median age of 55.5 years. All patients underwent radical surgery after neoadjuvant therapy, 14 patients received low anterior resection, 14 patients received abdominal perineal resection, and the other 2 patients received Hartmann procedure. All patients achieved R0 resection with a median operative time 220 minutes and the median intraoperative blood loss was 200 ml. The morbidity of postoperative complications was 20% (6/30), including dysuria in 2 patients, delayed healing of perineal incision in 2 patients, intestinal obstruction in 1 patient and pelvic hemorrhage in 1 patient. The median time to first flatus after surgery was 3 days and the median postoperative hospital stay was 8 days. Postoperative pathological results showed that 15 patients (50.0%) had severe tumor regression, including 4 patients (13.3%) achieved pathological complete response (pCR), 12 patients (40.0%) had moderate tumor regression, and 3 patients (10.0%) had minor tumor regression. Twenty patients had detailed pre-treatment clinical stage, and among those 20 patients, 15 patients (75.0%) and 13 patients (65.0%) achieved downstaging of tumor T stage and N stage, respectively. Only 2 patients appeared distant metastasis, and no patient had local recurrence.Conclusions:For locally advanced rectal cancer patients, mTNT doesn′t increase the morbidity of postoperative complication and is a safe and effective treatment strategy with satisfactory short-term result.

Objective:To analyze the clinical-pathological data of patients with locally advanced rectal cancer who underwent modified total neoadjuvant therapy (TNT), and to evaluate the safety and efficacy of radical surgery after modified total neoadjuvant therapy.Methods:The clinical-pathological data of 30 locally advanced rectal cancer patients who underwent modified TNT (mTNT) followed by radical resection were retrospectively analyzed. The surgical procedure, postoperative complications, tumor regression grade, tumor downstaging and prognosis were analyzed.Results:The 30 patients included 24 males and 6 females with a median age of 55.5 years. All patients underwent radical surgery after neoadjuvant therapy, 14 patients received low anterior resection, 14 patients received abdominal perineal resection, and the other 2 patients received Hartmann procedure. All patients achieved R0 resection with a median operative time 220 minutes and the median intraoperative blood loss was 200 ml. The morbidity of postoperative complications was 20% (6/30), including dysuria in 2 patients, delayed healing of perineal incision in 2 patients, intestinal obstruction in 1 patient and pelvic hemorrhage in 1 patient. The median time to first flatus after surgery was 3 days and the median postoperative hospital stay was 8 days. Postoperative pathological results showed that 15 patients (50.0%) had severe tumor regression, including 4 patients (13.3%) achieved pathological complete response (pCR), 12 patients (40.0%) had moderate tumor regression, and 3 patients (10.0%) had minor tumor regression. Twenty patients had detailed pre-treatment clinical stage, and among those 20 patients, 15 patients (75.0%) and 13 patients (65.0%) achieved downstaging of tumor T stage and N stage, respectively. Only 2 patients appeared distant metastasis, and no patient had local recurrence.Conclusions:For locally advanced rectal cancer patients, mTNT doesn′t increase the morbidity of postoperative complication and is a safe and effective treatment strategy with satisfactory short-term result.

Objective To evaluate the short?term and long?term efficacy of endoscopic submucosal dissection (ESD) in the treatment of early low rectal cancer and precancerous lesions. Methods Inclusion criteria: (1) Distance from the lower margin of tumor to the anal was ≤5 cm. (2) Early low rectal cancers were any size rectal epithelial tumors with infiltration depth limited to the mucosa and submucosa, which were diagnosed by postoperative pathology as high?grade intraepithelial neoplasia or adenocarcinoma of the rectum with infiltration depth of intramucosal or submucosal cancer (M or SM stage). (3) Precancerous lesions included adenoma and low?grade intraepithelial neoplasia of the rectum. (4) Patients received ESD treatment. Patients with tumor invasion depth over submucosa by pathology were excluded. From January 2008 to January 2018, 63 patients meeting the above criteria in Peking University First Hospital were enrolled in this descriptive cohort study. The disease characteristics, clinical manifestations, pathological types, treatment time, hospitalization time, en bloc resection rate (resection of the whole lesion), complete resection rate (both the horizontal and vertical incision margins were negative), postoperative complications and follow?up results were analyzed. Cummulative survival rate was calculated by Kaplan?Meier. Results The diameter of the lesion was (29.0 ± 23.4) mm and the distance from the lesion to the anus was (2.7±1.8) cm. The median operation time was 45.0 (range, 10.0 to 360.0) minutes, the median hospitalization time was 3.0 (range, 2.0 to 12.0) days, en bloc resection rate was 100%, complete resection rate was 96.8% (61/63), and 1 case (1.6%) had postoperative bleeding. The follow?up rate was 87.3% (55/63) and the median follow?up time was 57.9 (range, 15.6 to 121.1) months. No local recurrence was found during the follow?up period and the 5?year survival rate was 100%. Conclusion Short?and long?term efficacy of ESD are quite good in the treatment of patients with early low rectal cancer and precancerous lesions.

Objective To evaluate the short?term and long?term efficacy of endoscopic submucosal dissection (ESD) in the treatment of early low rectal cancer and precancerous lesions. Methods Inclusion criteria: (1) Distance from the lower margin of tumor to the anal was ≤5 cm. (2) Early low rectal cancers were any size rectal epithelial tumors with infiltration depth limited to the mucosa and submucosa, which were diagnosed by postoperative pathology as high?grade intraepithelial neoplasia or adenocarcinoma of the rectum with infiltration depth of intramucosal or submucosal cancer (M or SM stage). (3) Precancerous lesions included adenoma and low?grade intraepithelial neoplasia of the rectum. (4) Patients received ESD treatment. Patients with tumor invasion depth over submucosa by pathology were excluded. From January 2008 to January 2018, 63 patients meeting the above criteria in Peking University First Hospital were enrolled in this descriptive cohort study. The disease characteristics, clinical manifestations, pathological types, treatment time, hospitalization time, en bloc resection rate (resection of the whole lesion), complete resection rate (both the horizontal and vertical incision margins were negative), postoperative complications and follow?up results were analyzed. Cummulative survival rate was calculated by Kaplan?Meier. Results The diameter of the lesion was (29.0 ± 23.4) mm and the distance from the lesion to the anus was (2.7±1.8) cm. The median operation time was 45.0 (range, 10.0 to 360.0) minutes, the median hospitalization time was 3.0 (range, 2.0 to 12.0) days, en bloc resection rate was 100%, complete resection rate was 96.8% (61/63), and 1 case (1.6%) had postoperative bleeding. The follow?up rate was 87.3% (55/63) and the median follow?up time was 57.9 (range, 15.6 to 121.1) months. No local recurrence was found during the follow?up period and the 5?year survival rate was 100%. Conclusion Short?and long?term efficacy of ESD are quite good in the treatment of patients with early low rectal cancer and precancerous lesions.

Objective: To evaluate the short-term and long-term efficacy of endoscopic submucosal dissection (ESD) in the treatment of early low rectal cancer and precancerous lesions. Methods: Inclusion criteria: (1) Distance from the lower margin of tumor to the anal was ≤ 5 cm. (2) Early low rectal cancers were any size rectal epithelial tumors with infiltration depth limited to the mucosa and submucosa, which were diagnosed by postoperative pathology as high-grade intraepithelial neoplasia or adenocarcinoma of the rectum with infiltration depth of intramucosal or submucosal cancer (M or SM stage). (3) Precancerous lesions included adenoma and low-grade intraepithelial neoplasia of the rectum. (4) Patients received ESD treatment. Patients with tumor invasion depth over submucosa by pathology were excluded. From January 2008 to January 2018, 63 patients meeting the above criteria in Peking University First Hospital were enrolled in this descriptive cohort study. The disease characteristics, clinical manifestations, pathological types, treatment time, hospitalization time, en bloc resection rate (resection of the whole lesion), complete resection rate (both the horizontal and vertical incision margins were negative), postoperative complications and follow-up results were analyzed. Cummulative survival rate was calculated by Kaplan-Meier. Results: The diameter of the lesion was (29.0±23.4) mm and the distance from the lesion to the anus was (2.7±1.8) cm. The median operation time was 45.0 (range, 10.0 to 360.0) minutes, the median hospitalization time was 3.0 (range, 2.0 to 12.0) days, en bloc resection rate was 100%, complete resection rate was 96.8% (61/63), and 1 case (1.6%) had postoperative bleeding. The follow-up rate was 87.3% (55/63) and the median follow-up time was 57.9 (range, 15.6 to 121.1) months. No local recurrence was found during the follow-up period and the 5-year survival rate was 100%. Conclusion Short- and long-term efficacy of ESD are quite good in the treatment of patients with early low rectal cancer and precancerous lesions.